Skip to yearly menu bar Skip to main content


Poster

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks

Yarin Gal · Zoubin Ghahramani

Area 5+6+7+8 #22

Keywords: [ Deep Learning or Neural Networks ] [ Variational Inference ]


Abstract:

Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers. Recent results at the intersection of Bayesian modelling and deep learning offer a Bayesian interpretation of common deep learning techniques such as dropout. This grounding of dropout in approximate Bayesian inference suggests an extension of the theoretical results, offering insights into the use of dropout with RNN models. We apply this new variational inference based dropout technique in LSTM and GRU models, assessing it on language modelling and sentiment analysis tasks. The new approach outperforms existing techniques, and to the best of our knowledge improves on the single model state-of-the-art in language modelling with the Penn Treebank (73.4 test perplexity). This extends our arsenal of variational tools in deep learning.

Live content is unavailable. Log in and register to view live content